Artificial Intelligence Model for Predicting the Onboarding Time of Candidates to Loyal Logistics Company Based on Their Sociodemographic Characteristics

Abstract

The problem addressed in this project focuses on personnel selection within organizations, a crucial process managed by the human resources department to identify the ideal candidate. Despite being fundamental, as per Lazzari et al. (1999), not all companies conduct it efficiently, leading to issues such as staff turnover, reduced productivity, and a poor work environment.

The project arises in response to the need to enhance personnel selection processes at Loyal Logistics, which faces high turnover, especially in roles like Load and Unload Assistants and Drivers. The proposal involves implementing an Artificial Intelligence Model that analyzes candidates' sociodemographic characteristics and efficiently predicts their time of engagement, aiming to optimize the selection process.

Data analysis stands out as a key tool to improve selection processes, reducing time and manual work. The use of Big Data during the process can lead to cost reduction by avoiding erroneous hires and the associated expenses related to training and a second selection process.

Project objectives include collecting and cleaning sociodemographic data, identifying relevant and predictive variables, and training an Artificial Intelligence model. The justification is based on the growing importance of data analysis in human resources, specifically HR analytics, aiming to explore concepts that solve organizational problems related to human resources.

In conclusion, the project seeks to address the challenge of high personnel turnover at Loyal Logistics by implementing a predictive model based on artificial intelligence. This leverages candidates' sociodemographic characteristics to enhance efficiency in the personnel selection process.